class AugmentingParallelBatchIterator(ParallelBatchIterator):
"""
Randomly changes images in the batch. Behaviour can be defined in params.py.
"""
def __init__(self,
keys,
batch_size,
std,
mean,
coates_features=None,
y_all=None,
n_eyes=1):
super(AugmentingParallelBatchIterator, self).__init__(keys,
batch_size,
std,
mean,
coates_features,
y_all,
n_eyes=n_eyes)
# Initialize augmenter
self.augmenter = Augmenter()
def transform(self, Xb, yb):
Xbb = self.augmenter.augment(Xb)
# Do normalization in super-method
Xbb, yb = super(AugmentingParallelBatchIterator,
self).transform(Xbb, yb)
return Xbb, yb
def read_and_augment(keys):
augmenter = Augmenter()
images = np.zeros( (len(keys),CHANNELS,PIXELS,PIXELS), dtype=np.float32)
for i, key in enumerate(keys):
image = scipy.misc.imread(IMAGE_SOURCE + "/" + 'train' + "/" + key + ".jpeg").transpose(2, 0, 1)
image = image/256.0
images[i] = image
return augmenter.augment(images)
def read_and_augment(keys):
augmenter = Augmenter()
images = np.zeros((len(keys), CHANNELS, PIXELS, PIXELS), dtype=np.float32)
for i, key in enumerate(keys):
image = scipy.misc.imread(IMAGE_SOURCE + "/" + 'train' + "/" + key +
".jpeg").transpose(2, 0, 1)
image = image / 256.0
images[i] = image
return augmenter.augment(images)
class AugmentingParallelBatchIterator(ParallelBatchIterator): """ Randomly changes images in the batch. Behaviour can be defined in params.py. """ def __init__(self, keys, batch_size, std, mean, coates_features = None, y_all = None, n_eyes=1): super(AugmentingParallelBatchIterator, self).__init__(keys, batch_size, std, mean, coates_features, y_all, n_eyes=n_eyes) # Initialize augmenter self.augmenter = Augmenter() def transform(self, Xb, yb): Xbb = self.augmenter.augment(Xb) # Do normalization in super-method Xbb, yb = super(AugmentingParallelBatchIterator, self).transform(Xbb, yb) return Xbb, yb
print "Training for {} epochs".format(num_epochs)
curves = {'train_loss': [], 'val_loss': [], 'val_acc': []}
for epoch in range(num_epochs):
# In each epoch, we do a full pass over the training data...
train_err = 0
train_batches = 0
start_time = time.time()
aug_time = 0
for batch in tqdm(iterate_minibatches(train_X, train_y, 256, shuffle=True)):
inputs, targets = batch
if params.AUGMENT:
pre_aug = time.time()
inputs_augmented = a.augment(inputs)
aug_time+= (time.time() - pre_aug)
#Show unaugmented and augmented images
#visualize_data(np.append(inputs[:8],inputs_augmented[:8],axis=0).transpose(0,2,3,1))
inputs_augmented = normalize.normalize(inputs_augmented, mean, std)
train_err += train_fn(inputs_augmented, targets)
else:
#print inputs.shape,targets.shape
train_err += train_fn(inputs, targets)
train_batches += 1
#print "Augmentation time: ", aug_time
# ...and a full pass over the validation data
val_err = 0